Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| middle-tool 2514385224/middle-tool Provides a unified MCP server to interact with multiple middleware (Loki, MySQL, Redis, RocketMQ, Elasticsearch, MongoDB) through a desktop application for connection management and configuration export. | |
| Alexa+ MCP Assistant 25158074-alt/alexa-mcp-assistant Enables users to connect a browser workbench to a Streamable HTTP MCP endpoint for natural-language planning, approval-gated tool execution, and simulated home/calendar interactions, with Agent Skills and optional browser speech controls. | |
| remote-mcp-server-authless 2545142979/remote-mcp-server-authless Enables deploying a remote MCP server on Cloudflare Workers without authentication, with customizable tools for use with AI Playground or Claude Desktop. | |
| web2kb 2578d/web2kb Enables AI assistants to fetch webpages, convert them to Markdown, index into SQLite FTS5, and query the knowledge base through MCP tools. | |
| product-feedback-mcp 25andresbernal/product-feedback-mcp Enables triaging product feedback over a local dataset, including search, theme clustering, severity tagging, and drafting PRD-ready problem statements. | |
| semantic-model-kit 25andresbernal/semantic-model-kit Enables agents to query governed metrics through MCP, including describing metrics, running deterministic SQL against a warehouse, explaining join path preferences, and searching semantically ambiguous terms. | |
| IITM Live MCP Server 25ds1000090-lang/live-mcp-server Deploys a Streamable HTTP MCP server with one tool solve_challenge that computes a SHA-256 hash from a challenge header. | |
| Weather MCP Server 264gaurav/mcp_ai Demonstrates creating and connecting an MCP weather server using FastMCP, with support for integration with Claude Desktop, Cursor, and local LLMs to query weather alerts and information. | |
| RemoteMCP 264nm/lovensemax2-mcp-schedex An MCP server for controlling Lovense toys via local API, with multi-channel scripting, validated inputs, and physiologically-grounded presets. | |
| reliable-ssh-mcp 2667741708/reliable-ssh-mcp A local MCP server that enables running structured commands and fleet operations on SSH hosts, supporting secure file transfer, persistent sessions, and bastion-based discovery. | |
| miwifi-mcp 2670321532/miwifi-mcp Enables AI assistants to interact with Xiaomi/Redmi routers, providing read-only queries and management capabilities such as device listing, port forwarding, DHCP reservations, and reboot control. | |
| agentbrain 2672243194/agentbrain Local-first long-term memory for AI agents via a Markdown vault, offering MCP tools to query, ingest, lint, distill, and manage agent lessons and profile suggestions. | |
| AAS Core (agentic-awesome-skills-mcp) 26bb/agentic-awesome-skills-mcp A local, read-only MCP server that lets coding agents search the complete AAS skill catalog, compose and validate agent-chosen skill stacks, and generate reproducible, reviewable plans without uploading project code. | |
| Resume MCP Server 26ritika/resume-mcp An MCP server that compares your resume against a job description using semantic similarity and keyword matching, and generates a visual skill-gap chart. | |
| OpenClaw/Codex Read-only MCP 26s5k7yty4-boop/openclaw-codex-readonly-mcp Provides read-only access to OpenClaw and Codex operational data like status, tasks, sessions, logs, and Git changes. Ensures safety via redaction, allowlists, and bounded outputs. | |
| Zhipu Text-to-Image MCP Server 2716025420/mcp-zhipu-text-to-image-kuma Enables text-to-image generation using Zhipu AI's CogView-4 API. Supports generating images from text prompts with configurable size and quality parameters through MCP-compatible clients like Claude Desktop and Cline. | |
| SUMIT MCP 27180781/mcp-sumit Enables AI assistants to interact with the SUMIT business management platform, including accounting, documents, credit card payments, CRM, inventory, and organization management, with support for multiple SUMIT accounts and secure authentic | |
| wechat-ai-assistant-public 2718704495-eng/wechat-ai-assistant-public Enables macOS WeChat desktop clients to read conversations via OCR, retrieve encrypted session memory, and perform controlled message sending through MCP with dry-run and supervised safeguards. | |
| GitHub App MCP gateway 2745518585/github-mcp-multi-id-gateway Enables GitHub MCP tools to target multiple GitHub App installations by selecting a repository, organization, or user scope per request. | |
| frida_mcp 276793422/frida_mcp MCP server for Frida dynamic instrumentation, enabling AI agents to enumerate devices/processes, attach, inject JavaScript, hook functions, read memory, and collect results via MCP tools. | |
| windbg_mcp 276793422/windbg_mcp MCP server that exposes WinDbg/cdb as a session-based debugging tool, allowing users to open dumps, launch/attach processes, and execute arbitrary cdb commands with persistent context across commands. | |
| 自媒体文案助手 MCP Server 279458179/wenan-mcp 提供热点获取、图片分析和成品文案生成等MCP工具，帮助AI Agent直接生成小红书、抖音等平台的可复制粘贴文案。 | |
| API易 MCP Server 2799662352/apiyi-mcp-server Enables Gemini-powered multimodal analysis (video, audio, image, documents), Google search, and code execution via the API易 service. Supports Docker deployment and flexible configuration. | |
| BMAD Agent FastMCP Service 2799662352/bmad-agent-fastmcp A professional AI agent system that provides 10+ specialized agents and 25+ MCP tools to support development workflows in Cursor IDE, with dual LLM mode support (built-in and DeepSeek API). | |
| Survey Cross-Analysis MCP Server 2811jh/survey-crosstable-mcp1.0.1 An AI-driven tool for processing survey data that supports cross-tabulation, NPS and satisfaction scoring, and automated Excel report generation. It enables users to analyze datasets via natural language for tasks like merging response opti | |
| itick-mcp-server 281287994w-art/itick-mcp-server Exposes iTick REST API as MCP tools, providing market data for stocks, crypto, forex, indices, futures, and funds including tick, quote, depth, and kline. | |
| mcp-shared-gateway 2836603852/mcp-shared-gateway Enables multiple AI agent sessions and sub-agents to share single running instances of configured tool backends, reducing process and memory overhead, stopping idle backends automatically, and exposing a compact set of meta-tools for discov | |
| zibel 286486/kalamo Enables AI agents to create and edit vector drawing documents over MCP, with tools to draw shapes, read document outlines, and render PNG previews while humans work in the same Illustrator-style canvas. | |
| HACOO MCP Server 2892778775/hacoo Enables multi-agent orchestration of digital IC design flows (DFT, synthesis, APR, STA, PV, IREM, thermal, SIPI) through natural language by integrating heterogeneous EDA tools into a unified, secure, and observable API space with per-agent | |
| Indian News Sports Aggregator 28shekhar/mcp-sports-aggregator MCP server that aggregates and caches top stories from Indian news websites, prioritizing sports stories, and exposes them via tools for use with Claude. | |
| StudyFlow MCP 2924547961/studyflow Enables controlled browser-assisted learning workflows on course portals, including account/session observation, chapter navigation, quiz and exam review, video/media inspection, deadline and wrong-question tracking, and optional email noti | |
| visio-mcp-sci 2924547961/visio-mcp-sci A Windows MCP server for creating fully editable Microsoft Visio diagrams with compact SCI/IEEE styling, native arrowheads, obstacle-aware routing, and a pre-export geometry audit. | |
| Civ6 MCP CN 2962348318-del/civ6-mcp-cn Enables AI clients to read and control Civilization VI game state through FireTuner, execute actions, enforce turn-completion checks, and retain long-term strategy context. Supports a shared local HTTP connection so multiple MCP clients can | |
| MCP Unity 2996371275/unity_mcp_complex Implementation of the Model Context Protocol for Unity Editor, allowing AI assistants to interact with Unity projects through a Node.js server bridge. | |
| job-radar 2b1q/job-radar Enables searching and managing job postings across multiple job boards through a unified MCP interface, with deduplication and persistent tracking of application statuses. | |
| calibre-mcp 2b3pro/calibre-mcp Enables searching, reading, and managing a Calibre ebook library through natural language, with features like metadata search, full-text search, content extraction, and library management. | |
| markdown2pdf-mcp 2b3pro/markdown2pdf-mcp An MCP server for converting Markdown documents to PDF files. | |
| propublica-npo-mcp 2b3pro/propublica-npo-mcp Provides tools to search and retrieve nonprofit organization data and IRS filing summaries from ProPublica's Nonprofit Explorer, including side-by-side comparisons. | |
| Roam Research 2b3pro/roam-research-mcp Provides comprehensive access to Roam Research's API functionality. This server enables AI assistants like Claude to interact with your Roam Research graph through a standardized interface. | |
| ME4-YOUTUBE 2bai4me/me4-service-youtube YouTube Content Extraction Service for the ME4 suite, enabling download, metadata, transcripts, and comments via MCP, HTTP, and ZMQ interfaces. | |
| Enhanced iTerm MCP Server 2black0/enhanced-iterm-mcp-server Provides advanced iTerm2 terminal automation using Python API integration, enabling AI assistants to create and manage terminal sessions, split panes, execute commands, broadcast to multiple panes, and monitor terminal state in real-time. | |
| Qiita MCP Server 2bo/qiita-mcp-server A Model Context Protocol server that enables AI agents to interact with Qiita, allowing for creating, reading, and updating articles through standardized MCP tools. | |
| Garoon MCP Server 2ca3/garoon-mcp-server A Model Context Protocol (MCP) server that integrates Cybozu's Garoon groupware, enabling schedule management, meeting scheduling, and user search through natural language. | |
| mcp-captcha-solver 2captcha/mcp-captcha-solver Provides browser automation and reCAPTCHA v2 solving tools for AI agents, integrating Selenium and 2Captcha. | |
| Kaiten MCP 2chevskii/kaiten-mcp Connects an AI assistant to a Kaiten workspace through 44 tools that search and read cards, browse spaces, boards, columns and lanes, and create, update, move, archive or delete cards along with their comments, members, tags, checklists and | |
| 2dai-mcp-server 2daicommunity/2dai-mcp-server MCP server for 2DAI that enables AI assistants to generate images and videos, upload references, browse the public feed, and manage cloud drive on a 2DAI account. | |
| naver-ads-mcp 2duckchun/naver-ads-mcp Enables MCP clients such as Claude Code and Claude Desktop to retrieve Naver Search Ads campaigns, ad groups, keywords, ads, extensions, business channels, customer links, and performance metrics through read-only tools. | |
| mealie-mcp 2fst4u/mealie-mcp Exposes every endpoint of the Mealie REST API as MCP tools, enabling LLMs to manage recipes, meal plans, shopping lists, and more. | |
| Excalidraw MCP App Server 2gavy/excalidraw-mcp1 Enables users to create and interact with hand-drawn Excalidraw diagrams featuring smooth viewport camera control and interactive fullscreen editing. It uses the MCP Apps extension to render collaborative virtual whiteboards directly within | |
| dart-mcp 2geonhyup/dart-mcp dart-mcp |
22,001–22,050 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.